Back to all models
Get all the details on GPT-4o, an AI model from OpenAI. This page covers its token limits, pricing structure, key capabilities such as distillation, fine_tuning, function_calling, available API code samples, and performance strengths.
Key Metrics
Input Limit
128K tokens
Output Limit
16.4K tokens
Input Cost
$2.50/1M
Output Cost
$10.00/1M
Sample API Code
from openai import OpenAI
client = OpenAI()
response = client.chat.completions.create(
model="gpt-4o",
messages=[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Hello!"}
]
)
print(response.choices[0].message.content)Required Libraries
openai
openai
Benchmarks
| Benchmark | Score | Source | Notes |
|---|---|---|---|
1265 | lmarena.ai | Score for gpt-4o-2024-08-06, the default alias for gpt-4o | |
1126 | lmarena.ai | Score for gpt-4o-2024-08-06, the default alias for gpt-4o | |
53.95 | LiveBench | Score for 'GPT-4o' | |
39.75 | LiveBench | Score for 'GPT-4o' | |
69.29 | LiveBench | Score for 'GPT-4o' | |
41.48 | LiveBench | Score for 'GPT-4o' | |
63.53 | LiveBench | Score for 'GPT-4o' | |
44.68 | LiveBench | Score for 'GPT-4o' | |
64.94 | LiveBench | Score for 'GPT-4o' | |
72.08 | Vellum | Score for 'GPT-4o' | |
13.4 | Vellum | Score for 'GPT-4o' | |
56.1 | Vellum | Score for 'GPT-4o' | |
31 | Vellum | Score for 'GPT-4o' | |
60.3 | Vellum | Score for 'GPT-4o' |
Notes
GPT-4o (“o” for “omni”) is OpenAI's versatile, high-intelligence flagship model. It accepts both text and image inputs, and produces text outputs (including Structured Outputs). It is the best model for most tasks, and is OpenAI's most capable model outside of their o-series models.
Capabilities
distillation
fine tuning
function calling
multimodal input
predicted outputs
streaming
structured outputs
web browsing via tool
Supported Data Types
Input Types
text
image
Output Types
text
Strengths & Weaknesses
Exceptional at
general versatility
high intelligence
multimodal understanding
tool use
Good at
coding
instruction following
structured outputs
function calling
vision tasks
Poor at
reasoning
mathematics
language
Additional Information
Latest Update
Nov 20, 2024
Knowledge Cutoff
Oct 1, 2023